// Use this tool when you need up-to-date web search results from Exa MCP. It calls `web_search_exa` over `text/event-stream`, supports optional `exaApiKey`, and returns extracted text content from search results.
| name | exa-search |
| description | Use this tool when you need up-to-date web search results from Exa MCP. It calls `web_search_exa` over `text/event-stream`, supports optional `exaApiKey`, and returns extracted text content from search results. |
| metadata | {"openclaw":{"emoji":"🔎","requires":{"bins":["node"]}}} |
通过 Exa MCP (https://mcp.exa.ai/mcp) 执行 web_search_exa，并解析 text/event-stream 响应。
环境变量 EXA_API_KEY 可选, 可在 https://dashboard.exa.ai/api-keys 获取
node {baseDir}/scripts/search.mjs "today is 2026-02-09
美国最新娱乐新闻"
node {baseDir}/scripts/search.mjs "美国最新娱乐新闻" --num-results 5 --type auto --livecrawl fallback
node {baseDir}/scripts/search.mjs "美国最新娱乐新闻" --exa-api-key YOUR_EXA_KEY
EXA_API_KEY=YOUR_EXA_KEY node {baseDir}/scripts/search.mjs "美国最新娱乐新闻"
--type <value>: Exa 搜索类型，默认 auto--num-results <number>: 返回条数，默认 5--livecrawl <value>: 实时抓取策略，默认 fallback--exa-api-key <key>: 可选 API Key；传入后会自动拼接到 URL ?exaApiKey=...--endpoint <url>: 可选 MCP endpoint，默认 https://mcp.exa.ai/mcp--timeout <ms>: 请求超时毫秒，默认 30000--raw: 输出原始 text/event-stream，不做解析Notes:
https://mcp.exa.ai/mcp?exaApiKey=YOUR_EXA_KEY 为可选写法--endpoint 已包含 exaApiKey，脚本不会重复追加event: message 的 data JSON 中 result.content[].textUse this when you need the raw HTTP response for non-HTML content or APIs. Examples: JSON, XML, RSS/Atom, CSV, plain text, files, or downloads. If the target is a human-readable web page (HTML) that should be converted to markdown, use fetch-webpage instead.
Fetch webpages into Markdown by URL, with a selectable --provider parameter for pure.md, defuddle.md, markdown.new, or r.jina.ai.
Use this tool when you need up-to-date information from the internet. It grounds the model with real-time Google Search results across languages, improving factual accuracy and enabling responses with verifiable citations beyond the model's knowledge cutoff.
Use Ollama Cloud web APIs for single-query web search and single-page web fetch. Requires OLLAMA_API_KEY and uses shell HTTP requests, preferably curl.
Generate images using the Pollinations.ai API. Supports models such as flux, zimage, imagen-4, klein, klein-large, gptimage (free), and seedream, kontext, nanobanana, gptimage-large (paid). Use when the user asks to generate, create, or draw images from text prompts.